
import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
import plotly.express as px
import plotly.graph_objects as go
import squarify
import missingno as mn
from wordcloud import WordCloud, STOPWORDS


data_frame = pd.read_csv("US_Accidents_Dec20.csv")


data_frame


data_frame.head()


data_frame.tail()


data_frame.shape

(1516064, 47)


data_frame.index

RangeIndex(start=0, stop=1516064, step=1)


data_frame.describe()


data_frame.columns

Index(['ID', 'Severity', 'Start_Time', 'End_Time', 'Start_Lat', 'Start_Lng',
       'End_Lat', 'End_Lng', 'Distance(mi)', 'Description', 'Number', 'Street',
       'Side', 'City', 'County', 'State', 'Zipcode', 'Country', 'Timezone',
       'Airport_Code', 'Weather_Timestamp', 'Temperature(F)', 'Wind_Chill(F)',
       'Humidity(%)', 'Pressure(in)', 'Visibility(mi)', 'Wind_Direction',
       'Wind_Speed(mph)', 'Precipitation(in)', 'Weather_Condition', 'Amenity',
       'Bump', 'Crossing', 'Give_Way', 'Junction', 'No_Exit', 'Railway',
       'Roundabout', 'Station', 'Stop', 'Traffic_Calming', 'Traffic_Signal',
       'Turning_Loop', 'Sunrise_Sunset', 'Civil_Twilight', 'Nautical_Twilight',
       'Astronomical_Twilight'],
      dtype='object')


print(data_frame.count(numeric_only=True))
print("Total No. of Numerical Columns:", len(data_frame.count(numeric_only=True)))

Severity             1516064
Start_Lat            1516064
Start_Lng            1516064
End_Lat              1516064
End_Lng              1516064
Distance(mi)         1516064
Number                469969
Temperature(F)       1473031
Wind_Chill(F)        1066748
Humidity(%)          1470555
Pressure(in)         1479790
Visibility(mi)       1471853
Wind_Speed(mph)      1387202
Precipitation(in)    1005515
Amenity              1516064
Bump                 1516064
Crossing             1516064
Give_Way             1516064
Junction             1516064
No_Exit              1516064
Railway              1516064
Roundabout           1516064
Station              1516064
Stop                 1516064
Traffic_Calming      1516064
Traffic_Signal       1516064
Turning_Loop         1516064
dtype: int64
Total No. of Numerical Columns: 27


import missingno as missnum
missing_val = data_frame.isna().sum().sort_values(ascending=False)
missing_percent = missing_val[missing_val!=0]/len(data_frame)*100


print(" Missing Values in %\n", missing_percent)

 Missing Values in %
 Number                   69.000715
Precipitation(in)        33.675953
Wind_Chill(F)            29.637007
Wind_Speed(mph)           8.499773
Humidity(%)               3.001786
Visibility(mi)            2.916170
Weather_Condition         2.902714
Temperature(F)            2.838469
Wind_Direction            2.760965
Pressure(in)              2.392643
Weather_Timestamp         1.996222
Airport_Code              0.280199
Timezone                  0.151841
Zipcode                   0.061673
Sunrise_Sunset            0.005475
Civil_Twilight            0.005475
Nautical_Twilight         0.005475
Astronomical_Twilight     0.005475
City                      0.005475
dtype: float64


null_columns = [i for i in data_frame.columns if data_frame[i].isnull().any()]
print(null_columns)

['Number', 'City', 'Zipcode', 'Timezone', 'Airport_Code', 'Weather_Timestamp', 'Temperature(F)', 'Wind_Chill(F)', 'Humidity(%)', 'Pressure(in)', 'Visibility(mi)', 'Wind_Direction', 'Wind_Speed(mph)', 'Precipitation(in)', 'Weather_Condition', 'Sunrise_Sunset', 'Civil_Twilight', 'Nautical_Twilight', 'Astronomical_Twilight']


data_frame.isnull().sum()

ID                             0
Severity                       0
Start_Time                     0
End_Time                       0
Start_Lat                      0
Start_Lng                      0
End_Lat                        0
End_Lng                        0
Distance(mi)                   0
Description                    0
Number                   1046095
Street                         0
Side                           0
City                          83
County                         0
State                          0
Zipcode                      935
Country                        0
Timezone                    2302
Airport_Code                4248
Weather_Timestamp          30264
Temperature(F)             43033
Wind_Chill(F)             449316
Humidity(%)                45509
Pressure(in)               36274
Visibility(mi)             44211
Wind_Direction             41858
Wind_Speed(mph)           128862
Precipitation(in)         510549
Weather_Condition          44007
Amenity                        0
Bump                           0
Crossing                       0
Give_Way                       0
Junction                       0
No_Exit                        0
Railway                        0
Roundabout                     0
Station                        0
Stop                           0
Traffic_Calming                0
Traffic_Signal                 0
Turning_Loop                   0
Sunrise_Sunset                83
Civil_Twilight                83
Nautical_Twilight             83
Astronomical_Twilight         83
dtype: int64


missnum.matrix(data_frame[null_columns]);


data_frame.dropna(inplace=True)


data_frame.isnull().sum()

ID                       0
Severity                 0
Start_Time               0
End_Time                 0
Start_Lat                0
Start_Lng                0
End_Lat                  0
End_Lng                  0
Distance(mi)             0
Description              0
Number                   0
Street                   0
Side                     0
City                     0
County                   0
State                    0
Zipcode                  0
Country                  0
Timezone                 0
Airport_Code             0
Weather_Timestamp        0
Temperature(F)           0
Wind_Chill(F)            0
Humidity(%)              0
Pressure(in)             0
Visibility(mi)           0
Wind_Direction           0
Wind_Speed(mph)          0
Precipitation(in)        0
Weather_Condition        0
Amenity                  0
Bump                     0
Crossing                 0
Give_Way                 0
Junction                 0
No_Exit                  0
Railway                  0
Roundabout               0
Station                  0
Stop                     0
Traffic_Calming          0
Traffic_Signal           0
Turning_Loop             0
Sunrise_Sunset           0
Civil_Twilight           0
Nautical_Twilight        0
Astronomical_Twilight    0
dtype: int64


data_frame.shape

(334821, 47)


missnum.matrix(data_frame[null_columns]);


data_frame.columns

Index(['ID', 'Severity', 'Start_Time', 'End_Time', 'Start_Lat', 'Start_Lng',
       'End_Lat', 'End_Lng', 'Distance(mi)', 'Description', 'Number', 'Street',
       'Side', 'City', 'County', 'State', 'Zipcode', 'Timezone',
       'Airport_Code', 'Weather_Timestamp', 'Temperature(F)', 'Wind_Chill(F)',
       'Humidity(%)', 'Pressure(in)', 'Visibility(mi)', 'Wind_Direction',
       'Wind_Speed(mph)', 'Precipitation(in)', 'Weather_Condition', 'Amenity',
       'Bump', 'Crossing', 'Give_Way', 'Junction', 'No_Exit', 'Railway',
       'Roundabout', 'Station', 'Stop', 'Traffic_Calming', 'Traffic_Signal',
       'Sunrise_Sunset', 'Civil_Twilight', 'Nautical_Twilight',
       'Astronomical_Twilight', 'Day_of_Week'],
      dtype='object')


from sklearn.model_selection import train_test_split
df1 = data_frame[[column for column in data_frame if data_frame[column].count() / len(data_frame) >= 0.3]]


data_frame.Severity.value_counts(normalize=True).sort_index().plot.bar()
plt.grid()
plt.title('Severity')
plt.xlabel('Severity')
plt.ylabel('');


boolean_columns = [col for col in data_frame.columns if data_frame[col].dtype ==np.dtype('bool')]
booleandf = data_frame[boolean_columns]
meta = booleandf[booleandf.sum(axis=1) > 1]
print('There are {} metadata rows, which are {:.1f}% of the data'.format(len(meta),100*len(meta)/len(data_frame)))

There are 39052 metadata rows, which are 11.7% of the data


booleans = booleandf.sum(axis=0)


booleans.plot.pie(figsize=(13,13))
plt.ylabel('')
plt.title('Proximity to Traffic');


start = pd.to_datetime(df.Start_Time, format='%Y-%m-%d %H:%M:%S')
end = pd.to_datetime(df.End_Time, format='%Y-%m-%d %H:%M:%S')


d = (end-start)
top20 = d.astype('timedelta64[m]').value_counts().nlargest(20)
print('Top 20 accident durations in US Accidents dataset data {:.1f}% '.format(top20.sum()*100/len(d)))
(top20/top20.sum()).plot.bar(figsize=(14,14))
plt.title('Overall Duration of Accident in Minutes')
plt.xlabel('Duration in Minutes')
plt.ylabel('Fraction');

Top 20 accident durations in US Accidents dataset data 37.3%


count_statewise = data_frame['State'].value_counts()
top10_statecount = count_statewise.iloc[:10]
other_statecount = {'Others': count_statewise.iloc[10:].values.sum()}
overall_count = top10_statecount.append(pd.Series(other_statecount))


overall_count

CA        77394
FL        53115
OR        27582
PA        17228
SC        15570
NC        14972
TX        13706
MN        12003
NY        11469
VA         9993
Others    81789
dtype: int64


plt.figure(figsize=(15, 10))
sns.barplot(top10_statecount.index, top10_statecount.values)
plt.show()

P:\UNCC Subjects\Machine Learning\Machine Learning Lab\lib\site-packages\seaborn\_decorators.py:36: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  warnings.warn(


fig = go.Figure(data=go.Choropleth(
    locations=count_statewise.index,
    z = count_statewise.values,
    locationmode = 'USA-states',
    colorscale = 'Reds',
    colorbar_title = "Accidents",
))
fig.update_layout(
    title_text = 'US Accidents States wise',
    geo_scope='usa',
    width=900, height=700
)
fig.show()


california = data_frame[data_frame['State'] == 'CA'].groupby('County').size().sort_values(ascending=False)
california.head()

County
Los Angeles       18642
Kern               4266
San Bernardino     3529
Riverside          2883
Fresno             2741
dtype: int64


plt.figure(figsize=(15, 10))
sns.barplot(california[:10].index, california[:10].values)
plt.show()

P:\UNCC Subjects\Machine Learning\Machine Learning Lab\lib\site-packages\seaborn\_decorators.py:36: FutureWarning:

Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.


plt.figure(figsize=(15, 10))
plt.pie(top10_statecount.values, labels=top10_statecount.index, autopct='%1.1f%%')
plt.show()


plt.figure(figsize=(15, 10))
data_frame.groupby('Weather_Condition').size().sort_values(ascending = False).iloc[:5].plot.pie(explode=[0.1,0,0,0,0],autopct='%1.1f%%',shadow=True)
plt.show()


data_frame['Start_Time'] = pd.to_datetime(data_frame['Start_Time'], infer_datetime_format=True)
data_frame['End_Time'] = pd.to_datetime(data_frame['Start_Time'], infer_datetime_format=True)
data_frame['Day_of_Week'] = data_frame['Start_Time'].dt.day_name()
weekday_data = data_frame.groupby('Day_of_Week').size().sort_values(ascending = False)
weekday_data.head()

Day_of_Week
Wednesday    55073
Thursday     54158
Friday       53505
Tuesday      52321
Monday       49018
dtype: int64


plt.figure(figsize=(13, 7))
sns.barplot(weekday_data.index, weekday_data.values)
plt.show()

P:\UNCC Subjects\Machine Learning\Machine Learning Lab\lib\site-packages\seaborn\_decorators.py:36: FutureWarning:

Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.


from sklearn.model_selection import train_test_split

y = data_frame['Severity']
x = data_frame.iloc[:,2:]

X_train, X_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=42)


X_train


X_test


y_train

271878    2
650573    2
942345    2
291539    2
262377    2
         ..
518354    2
933910    3
546628    2
582086    2
523260    2
Name: Severity, Length: 267856, dtype: int64


y_test

800489     2
1148669    2
783093     2
1035713    4
821532     2
          ..
1002997    2
253762     2
1016948    2
756570     2
284396     2
Name: Severity, Length: 66965, dtype: int64

	ID	Severity	Start_Time	End_Time	Start_Lat	Start_Lng	End_Lat	End_Lng	Distance(mi)	Description	...	Roundabout	Station	Stop	Traffic_Calming	Traffic_Signal	Turning_Loop	Sunrise_Sunset	Civil_Twilight	Nautical_Twilight	Astronomical_Twilight
0	A-2716600	3	2016-02-08 00:37:08	2016-02-08 06:37:08	40.10891	-83.09286	40.11206	-83.03187	3.230	Between Sawmill Rd/Exit 20 and OH-315/Olentang...	...	False	False	False	False	False	False	Night	Night	Night	Night
1	A-2716601	2	2016-02-08 05:56:20	2016-02-08 11:56:20	39.86542	-84.06280	39.86501	-84.04873	0.747	At OH-4/OH-235/Exit 41 - Accident.	...	False	False	False	False	False	False	Night	Night	Night	Night
2	A-2716602	2	2016-02-08 06:15:39	2016-02-08 12:15:39	39.10266	-84.52468	39.10209	-84.52396	0.055	At I-71/US-50/Exit 1 - Accident.	...	False	False	False	False	False	False	Night	Night	Night	Day
3	A-2716603	2	2016-02-08 06:15:39	2016-02-08 12:15:39	39.10148	-84.52341	39.09841	-84.52241	0.219	At I-71/US-50/Exit 1 - Accident.	...	False	False	False	False	False	False	Night	Night	Night	Day
4	A-2716604	2	2016-02-08 06:51:45	2016-02-08 12:51:45	41.06213	-81.53784	41.06217	-81.53547	0.123	At Dart Ave/Exit 21 - Accident.	...	False	False	False	False	False	False	Night	Night	Day	Day
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
1516059	A-4239402	2	2019-08-23 18:03:25	2019-08-23 18:32:01	34.00248	-117.37936	33.99888	-117.37094	0.543	At Market St - Accident.	...	False	False	False	False	False	False	Day	Day	Day	Day
1516060	A-4239403	2	2019-08-23 19:11:30	2019-08-23 19:38:23	32.76696	-117.14806	32.76555	-117.15363	0.338	At Camino Del Rio/Mission Center Rd - Accident.	...	False	False	False	False	False	False	Day	Day	Day	Day
1516061	A-4239404	2	2019-08-23 19:00:21	2019-08-23 19:28:49	33.77545	-117.84779	33.77740	-117.85727	0.561	At Glassell St/Grand Ave - Accident. in the ri...	...	False	False	False	False	False	False	Day	Day	Day	Day
1516062	A-4239405	2	2019-08-23 19:00:21	2019-08-23 19:29:42	33.99246	-118.40302	33.98311	-118.39565	0.772	At CA-90/Marina Fwy/Jefferson Blvd - Accident.	...	False	False	False	False	False	False	Day	Day	Day	Day
1516063	A-4239406	2	2019-08-23 18:52:06	2019-08-23 19:21:31	34.13393	-117.23092	34.13736	-117.23934	0.537	At Highland Ave/Arden Ave - Accident.	...	False	False	False	False	False	False	Day	Day	Day	Day

	ID	Severity	Start_Time	End_Time	Start_Lat	Start_Lng	End_Lat	End_Lng	Distance(mi)	Description	...	Roundabout	Station	Stop	Traffic_Calming	Traffic_Signal	Turning_Loop	Sunrise_Sunset	Civil_Twilight	Nautical_Twilight	Astronomical_Twilight
0	A-2716600	3	2016-02-08 00:37:08	2016-02-08 06:37:08	40.10891	-83.09286	40.11206	-83.03187	3.230	Between Sawmill Rd/Exit 20 and OH-315/Olentang...	...	False	False	False	False	False	False	Night	Night	Night	Night
1	A-2716601	2	2016-02-08 05:56:20	2016-02-08 11:56:20	39.86542	-84.06280	39.86501	-84.04873	0.747	At OH-4/OH-235/Exit 41 - Accident.	...	False	False	False	False	False	False	Night	Night	Night	Night
2	A-2716602	2	2016-02-08 06:15:39	2016-02-08 12:15:39	39.10266	-84.52468	39.10209	-84.52396	0.055	At I-71/US-50/Exit 1 - Accident.	...	False	False	False	False	False	False	Night	Night	Night	Day
3	A-2716603	2	2016-02-08 06:15:39	2016-02-08 12:15:39	39.10148	-84.52341	39.09841	-84.52241	0.219	At I-71/US-50/Exit 1 - Accident.	...	False	False	False	False	False	False	Night	Night	Night	Day
4	A-2716604	2	2016-02-08 06:51:45	2016-02-08 12:51:45	41.06213	-81.53784	41.06217	-81.53547	0.123	At Dart Ave/Exit 21 - Accident.	...	False	False	False	False	False	False	Night	Night	Day	Day

	Severity	Start_Lat	Start_Lng	End_Lat	End_Lng	Distance(mi)	Number	Temperature(F)	Wind_Chill(F)	Humidity(%)	Pressure(in)	Visibility(mi)	Wind_Speed(mph)	Precipitation(in)
count	1.516064e+06	1.516064e+06	1.516064e+06	1.516064e+06	1.516064e+06	1.516064e+06	4.699690e+05	1.473031e+06	1.066748e+06	1.470555e+06	1.479790e+06	1.471853e+06	1.387202e+06	1.005515e+06
mean	2.238630e+00	3.690056e+01	-9.859919e+01	3.690061e+01	-9.859901e+01	5.872617e-01	8.907533e+03	5.958460e+01	5.510976e+01	6.465960e+01	2.955495e+01	9.131755e+00	7.630812e+00	8.477855e-03
std	6.081481e-01	5.165653e+00	1.849602e+01	5.165629e+00	1.849590e+01	1.632659e+00	2.242190e+04	1.827316e+01	2.112735e+01	2.325986e+01	1.016756e+00	2.889112e+00	5.637364e+00	1.293168e-01
min	1.000000e+00	2.457022e+01	-1.244976e+02	2.457011e+01	-1.244978e+02	0.000000e+00	0.000000e+00	-8.900000e+01	-8.900000e+01	1.000000e+00	0.000000e+00	0.000000e+00	0.000000e+00	0.000000e+00
25%	2.000000e+00	3.385422e+01	-1.182076e+02	3.385420e+01	-1.182077e+02	0.000000e+00	1.212000e+03	4.700000e+01	4.080000e+01	4.800000e+01	2.944000e+01	1.000000e+01	4.600000e+00	0.000000e+00
50%	2.000000e+00	3.735113e+01	-9.438100e+01	3.735134e+01	-9.437987e+01	1.780000e-01	4.000000e+03	6.100000e+01	5.700000e+01	6.800000e+01	2.988000e+01	1.000000e+01	7.000000e+00	0.000000e+00
75%	2.000000e+00	4.072593e+01	-8.087469e+01	4.072593e+01	-8.087449e+01	5.940000e-01	1.010000e+04	7.300000e+01	7.100000e+01	8.400000e+01	3.004000e+01	1.000000e+01	1.040000e+01	0.000000e+00
max	4.000000e+00	4.900058e+01	-6.711317e+01	4.907500e+01	-6.710924e+01	1.551860e+02	9.999997e+06	1.706000e+02	1.130000e+02	1.000000e+02	5.804000e+01	1.400000e+02	9.840000e+02	2.400000e+01

	Start_Time	End_Time	Start_Lat	Start_Lng	End_Lat	End_Lng	Distance(mi)	Description	Number	Street	...	Roundabout	Station	Stop	Traffic_Calming	Traffic_Signal	Sunrise_Sunset	Civil_Twilight	Nautical_Twilight	Astronomical_Twilight	Day_of_Week
271878	2020-11-07 13:38:30	2020-11-07 13:38:30	39.936237	-75.142093	39.939962	-75.143373	0.266	Slow traffic from Washington Ave to I-95 N due...	789.0	S Christopher Columbus Blvd	...	False	False	False	False	False	Day	Day	Day	Day	Saturday
650573	2020-11-24 19:36:00	2020-11-24 19:36:00	33.993995	-117.941435	33.992981	-117.941334	0.070	Incident on HEATHER HILL RD near HOUSE 1639 Dr...	1637.0	Heather Hill Rd	...	False	False	False	False	False	Night	Night	Night	Night	Tuesday
942345	2020-04-28 10:56:23	2020-04-28 10:56:23	38.865590	-76.951310	38.865590	-76.951310	0.000	At Southern Ave - Accident.	3799.0	Alabama Ave SE	...	False	False	False	False	True	Day	Day	Day	Day	Tuesday
291539	2020-12-19 03:00:00	2020-12-19 03:00:00	36.384405	-119.296784	36.385534	-119.296739	0.078	NB SR63 JNO AVENUE 328. RP IN A GRY NISS MORAN...	32736.0	Road 124	...	False	False	False	False	False	Night	Night	Night	Night	Saturday
262377	2020-12-29 20:59:44	2020-12-29 20:59:44	35.278426	-80.858179	35.279245	-80.858575	0.061	Incident on DAWNSHIRE AVE near NORTHBROOK DR D...	3201.0	Dawnshire Ave	...	False	False	False	False	False	Night	Night	Night	Night	Tuesday
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
518354	2020-09-21 20:32:28	2020-09-21 20:32:28	40.019432	-76.341253	40.019052	-76.342442	0.068	Incident on MILLERSVILLE PIKE near GABLE PARK ...	1901.0	Millersville Pike	...	False	False	False	False	False	Night	Night	Night	Day	Monday
933910	2020-04-23 18:12:27	2020-04-23 18:12:27	41.709690	-87.779560	41.709690	-87.779560	0.000	At IL-43/S Harlem Ave - Accident.	10099.0	Southwest Hwy	...	False	False	False	False	True	Day	Day	Day	Day	Thursday
546628	2020-12-09 00:16:30	2020-12-09 00:16:30	38.978514	-77.249367	38.985086	-77.262616	0.844	Stationary traffic on VA-193 from Spring Hill ...	8915.0	Georgetown Pike	...	False	False	False	False	False	Night	Night	Night	Night	Wednesday
582086	2020-11-16 19:28:00	2020-11-16 19:28:00	29.653686	-82.496104	29.653890	-82.496079	0.014	Incident on SW 143RD ST near W NEWBERRY RD Dri...	32.0	SW 143rd St	...	False	False	False	False	True	Night	Night	Night	Night	Monday
523260	2020-10-27 22:40:10	2020-10-27 22:40:10	38.811299	-77.211792	38.811322	-77.210697	0.059	Incident on BRADDOCK RD near BRADDOCK RD Drive...	7817.0	Braddock Rd	...	False	False	False	False	False	Night	Night	Night	Night	Tuesday

	Start_Time	End_Time	Start_Lat	Start_Lng	End_Lat	End_Lng	Distance(mi)	Description	Number	Street	...	Roundabout	Station	Stop	Traffic_Calming	Traffic_Signal	Sunrise_Sunset	Civil_Twilight	Nautical_Twilight	Astronomical_Twilight	Day_of_Week
800489	2020-06-26 15:27:42	2020-06-26 15:27:42	40.121560	-76.059790	40.145220	-76.116550	3.415	Between PA-23/Main St and N Railroad Ave - Acc...	972.0	Weaverland Rd	...	False	False	False	False	False	Day	Day	Day	Day	Friday
1148669	2019-09-05 20:43:00	2019-09-05 20:43:00	37.698356	-122.118806	37.698356	-122.118806	0.000	At 167th Ave/Elgin St - Accident.	16001.0	Ashland Ave	...	False	False	False	False	True	Night	Night	Night	Day	Thursday
783093	2020-05-21 17:26:01	2020-05-21 17:26:01	39.887260	-83.057380	39.887260	-83.057380	0.000	At Gantz Rd - Accident.	3727.0	Gantz Rd	...	False	False	False	False	False	Day	Day	Day	Day	Thursday
1035713	2019-12-31 21:19:18	2019-12-31 21:19:18	42.427190	-73.660870	42.438270	-73.651210	0.910	Closed between Garrigan Rd and Parker Hall Rd ...	297.0	Garrigan Rd	...	False	False	False	False	False	Night	Night	Night	Night	Tuesday
821532	2020-06-11 14:38:51	2020-06-11 14:38:51	35.402380	-97.530170	35.402380	-97.530170	0.000	At I-240/Southwest Expy/SW 74th St - Accident.	6397.0	S Western Ave	...	False	False	True	False	False	Day	Day	Day	Day	Thursday
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
1002997	2020-02-14 14:02:00	2020-02-14 14:02:00	44.443170	-95.917700	44.443170	-95.917700	0.000	At CR-3/150th Ave - Vehicle spun around.	2500.0	190th Ave	...	False	False	False	False	False	Day	Day	Day	Day	Friday
253762	2020-11-20 00:30:00	2020-11-20 00:30:00	28.540728	-81.277423	28.541453	-81.277405	0.050	Incident on S CHICKASAW TRL near NEIGHBORHOOD ...	303.0	S Chickasaw Trl	...	False	False	False	False	False	Night	Night	Night	Night	Friday
1016948	2020-02-26 19:25:00	2020-02-26 19:25:00	37.691154	-122.093752	37.691154	-122.093752	0.000	At John Dr - Accident.	19998.0	Foothill Blvd	...	False	True	True	False	False	Night	Night	Night	Night	Wednesday
756570	2020-05-08 16:17:18	2020-05-08 16:17:18	43.210370	-77.600910	43.210370	-77.600910	0.000	At CR-91/Titus Ave - Accident.	2280.0	Hudson Ave	...	False	False	False	False	True	Day	Day	Day	Day	Friday
284396	2020-09-26 14:15:30	2020-09-26 14:15:30	25.763390	-80.336261	25.760970	-80.336170	0.167	Stationary traffic on FL-973 from W Flagler St...	782.0	SW 87th Ave	...	False	False	False	False	False	Day	Day	Day	Day	Saturday

Data Preprocessing¶

Import Libraries¶

Statistical Description of each column¶

Columns in dataframe¶

Numerical Columns to deal with¶

Check out the Missing Values¶

Getting List of Columns Having Null Values¶

Handling Missing Data of the dataset¶

Data After Dropping missing values¶

Data Understanding and Exploration Analysis¶

The feature Country has only one entry i.e USA, it is obvious since we are dealing with the USA’s dataset. so we will be deleting the feature Country.¶

The feature Turning_Loop has only one value — False. the feature actually means that no accidents were occured in the turning loops.¶

Severity¶

Most of the US Accidents i.e 0.8 have the severity 2 and followed by severity 4.¶

Proximity of the Traffic¶

Major percentage of the US Accidents are occured at traffic signals, Crossing, Station, Stop and Amenity. The least percentage of accidents are occured at Bump, Roundabout, Railway, No-Exit, Junction¶

Duration Of Top 20 Accidents¶

Most percentage of accidents are occured in California followed by florida.¶

Accident Analysis in California¶

As it is top most accident occured state¶

Bar Graph of California accidents¶

Pie Chart of California accidents¶

Weather Conditions Affecting Accidents¶

Accidents on Weekdays vs Weekends¶

Data Understanding from above Graphs¶

Data Preparation for Modeling - training and testing sets¶